© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150659
    Prev
    Next
    INDEX
    Explanations

    Quizizz works on every browser

    np_acts-logits-general · gemini-2.5-flash-lite

    concept assessment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EN
    0.53
    ους
    0.53
     rę
    0.51
    𝗩
    0.51
     wasn
    0.49
    ᱕
    0.49
     scopo
    0.49
     åp
    0.48
    Н
    0.48
    rę
    0.47
    POSITIVE LOGITS
    같은
    0.46
    agy
    0.45
     impairments
    0.45
    akir
    0.44
    yte
    0.43
    arat
    0.42
    trade
    0.41
    ipynb
    0.41
    }?
    0.40
    égi
    0.40
    Activations Density 0.000%

    No Known Activations